SimDocSin is a cross-lingual document similarity checking tool for Sinhala and English.
This system can be used to find similar documents or parts of documents of Sinhala (English) language to a given document of English (Sinhala) language. System consists of two parts.
Here an user can submit a source document to get any matching complete document that exists in the system database in target language. Here the user has to set 3 input fields. Those are:-
- Input language - Language of the source document. It can be Sinhala or English.
- Similarity level - This indicates how much similarity you expect from a similar pair output by system. The user can give a value within the range from 1 to 5. Low value means there is a high chance of getting a similar document but the similarity can be relatively low while high value means that system can output a document with a relatively high similarity but the chance of getting a result is low.
- Source file - Source document given as the input. It can be submitted as either a file or a text.
Here an user can submit a source document to get any matching partials of documents that exist in the system database in target language. Here also the user has to set the 3 inputs fields mentioned in the previous section. Apart from those there is another input field called Min Length. Min Length is the minimum number of sentences the user expected to have in a document partial. It can be 1, greater than 1, greater than 2, greater than 5 or greater than 10.
Udhan Isuranga (email@example.com)
Janaka Sandaruwan (firstname.lastname@example.org)
Udesh Athukorala (email@example.com)